DIY AI, deep learning network development for automated image classification in a point-of-care ultrasound quality assurance program.
Michael BlaivasRobert ArntfieldMatthew WhitePublished in: Journal of the American College of Emergency Physicians open (2020)
Our algorithm accurately classified 98% of new images, by body scan area, related to its training pool, simulating POCUS program workflow. Performance was diminished with exam images from an unrelated image pool and ultrasound equipment, suggesting additional images and convolutional neural network training are necessary for fine tuning when using across different POCUS programs. The algorithm showed theoretical potential to improve workflow for POCUS program directors, if fully implemented. The implications of our DIY AI for POCUS are scalable and further work to maximize the collaboration between AI and POCUS programs is warranted.
Keyphrases
- deep learning
- convolutional neural network
- artificial intelligence
- quality improvement
- machine learning
- magnetic resonance imaging
- public health
- electronic health record
- computed tomography
- air pollution
- virtual reality
- risk assessment
- magnetic resonance
- optical coherence tomography
- climate change
- contrast enhanced ultrasound